Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0000

Data Index: 444116 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6957. Min Act: -0.0000

Data Index: 866926 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6203. Min Act: -0.0000

Data Index: 498383 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5349. Min Act: -0.0000

Data Index: 755321 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5948. Min Act: -0.0000

Data Index: 157475 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5559. Min Act: -0.0000

Data Index: 459452 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5490. Min Act: -0.0000

Data Index: 926107 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5374. Min Act: -0.0000

Data Index: 886435 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5225. Min Act: -0.0000

Data Index: 366414 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4827. Min Act: -0.0000

Data Index: 391702 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4748. Min Act: -0.0000

Data Index: 666682 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4803. Min Act: -0.0000

Data Index: 869179 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4931. Min Act: -0.0000

Data Index: 319811 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1126334 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4740. Min Act: -0.0000

Data Index: 443875 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4561. Min Act: -0.0000

Data Index: 911420 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1170348 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4312. Min Act: -0.0000

Data Index: 499675 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4353. Min Act: -0.0000

Data Index: 408339 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4522. Min Act: -0.0000

Data Index: 949182 (C4 (Web Text))

Max Activating Token Index: 939